Instructions to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Crux-Qwen3_OpenThinking-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "prithivMLmods/Crux-Qwen3_OpenThinking-4B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

prithivMLmods commited on May 23, 2025

Commit

04912a9

verified ·

1 Parent(s): c4dfc40

Update README.md

Browse files

Files changed (1) hide show

README.md +51 -3

README.md CHANGED Viewed

@@ -1,3 +1,51 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+language:
+- en
+base_model:
+- prithivMLmods/Crux-Qwen3_OpenThinking-4B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text-generation-inference
+---
+# Crux-Qwen3\_OpenThinking-4B-GGUF
+> **Crux-Qwen3\_OpenThinking-4B** is fine-tuned on the **Qwen3-4B** architecture, optimized for advanced **open thinking**, **mathematical reasoning**, and **logical problem solving**. This model is trained on the traces of **sk1.1**, which include 1,000 entries from the **Gemini thinking trajectory**, combined with fine-tuning on 100k tokens of **open math reasoning** data. This makes it highly effective for nuanced reasoning, educational tasks, and complex problem-solving requiring clear thought processes.
+## Model Files
+| File Name                                     | Size    | Quantization | Format | Description                   |
+| --------------------------------------------- | ------- | ------------ | ------ | ----------------------------- |
+| `Crux-Qwen3_OpenThinking-4B-GGUF.F16.gguf`    | 8.05 GB | FP16         | GGUF   | Float16 precision version     |
+| `Crux-Qwen3_OpenThinking-4B-GGUF.Q4_K_M.gguf` | 2.5 GB  | Q4\_K\_M     | GGUF   | 4-bit quantized (K M variant) |
+| `Crux-Qwen3_OpenThinking-4B-GGUF.Q5_K_M.gguf` | 2.89 GB | Q5\_K\_M     | GGUF   | 5-bit quantized (K M variant) |
+| `Crux-Qwen3_OpenThinking-4B-GGUF.Q8_0.gguf`   | 4.28 GB | Q8\_0        | GGUF   | 8-bit quantized               |
+| `.gitattributes`                              | 1.88 kB | —            | —      | Git LFS tracking file         |
+| `config.json`                                 | 31 B    | —            | —      | Configuration file            |
+| `README.md`                                   | 31 B    | —            | —      | Model documentation           |
+## Quants Usage
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 16 bpw, overkill |
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)